Monthly Rainfall Forecasts Research Articles

Prakiraan Jumlah Curah Hujan Berdasarkan Data Parameter Cuaca Tahun 2011-2021 di Kota Pangkalpinang

Tropical weather prevails in the Pangkalpinang city region, complemented with a changeable rainy season that experiences monthly variations. This phenomena results in a considerable amount of precipitation in the city of Pangkalpinang, making the area known for its extreme rainfall. Using multiple linear regression approaches to anticipate monthly precipitation is the aim of this work. Rainfall (RR), air temperature (T), air humidity (RH), and air pressure are all part of the dataset that was collected over an 11-year period (2011–2021). The information was obtained from the meteorological station in Depati Amir Pangkalpinang. This study uses the multiple linear regression method. The rainfall forecast results are compared to the observed actual rainfall amounts. Based on air temperature and air humidity as predictors, the results show that the estimation of cumulative monthly precipitation in the Pangkalpinang city region for the year 2021 produced an average root mean square error (RSME) value of 112.6 mm/month. Furthermore, the T-test analysis produced a 0.9 result. With air temperature, humidity, and pressure as predictors, the total monthly rainfall for 2021 was predicted with an average root mean square error (RMSE) value of 107.9 mm/month. A T-test was also performed, and the result was 0.4. The results of this study show that the monthly rainfall forecast model for the city of Pangkalpinang that includes factors related to temperature, humidity, and pressure produces better results than the model that only includes these variables. November and December are the months with the greatest variations.

Hybridized gated recurrent unit with variational mode decomposition and an error compensation mechanism for multi-step-ahead monthly rainfall forecasting.

Highly accurate monthly rainfall predictions can provide early warnings for rain-related disasters, such as floods and droughts, and allow governments to make timely decisions. This paper proposes a two-phase error compensation model based on a gated recurrent unit (GRU), variational mode decomposition (VMD), and error compensation mechanism (ECM) (GRU-VMD-ECM) for accurate multi-step-ahead monthly rainfall forecasts. In the first phase, the GRU model is used to make an initial monthly rainfall prediction, and the error series is extracted. In the second phase, the error series is decomposed into eight subseries using the VMD method. Each subseries is then input into the GRU model to build different forecasting models. These predicted error sequences are added to the initial prediction results to obtain the final forecast. The model's performance is tested using six evaluation indicators based on Beijing's monthly rainfall data from 1951 to 2018. The results show that the error compensation mechanism significantly improved the prediction accuracy, particularly in the Nash-Sutcliffe efficiency (NSE) of single-step-ahead prediction which recorded a substantial increase of 281.16% from 0.259981 to 0.990944, as well as a decrease in root mean square error (RMSE) from 2.257580 to 0.249746. Furthermore, the GRU-VMD-ECM model outperforms the RF, GRU-CNN, and VMD-GRU models in terms of precision across all forecasting horizons. These findings highlight the potential of the GRU-VMD-ECM model in providing highly accurate monthly rainfall predictions for early warnings and informed decision-making by governments.

Rainfall forecast using SARIMA model along the coastal areas of Sindh Province

Rainfall forecasting is critical for economic activities such as agriculture, watershed management, and flood control. It requires mathematical modelling and simulation. This paper investigates the time series analysis and forecasting of the monthly rainfall for the Sindh coastline, Pakistan. The seasonal autoregressive integrated moving average (SARIMA) model was used for the last three decades (1991-2020) and forecasting was done for the next two years. The model is based on the Box Jenkins methodology. The decomposition of time series plots into trend, seasonal and random components showed a seasonal effect. The Augmented Dickey–Fuller (ADF) and Mann–Kendall (MK) tests showed the inherent stationarity of the rainfall data. The best SARIMA models for monthly rainfall were SARIMA (1,0,1)(3,1,1)12 and SARIMA (1,0,1)(1,1,1)12 with Akaike information criterion corrected (AICC) values of 1507 and 1387, respectively. The model predictions indicate that, in the years 2021/22, July will likely have the most rainfall, followed by August and June. The diagnostic statistical test values directed that the adequacy of the models is consistent for projected monthly rainfall forecasts.

Modeling of monthly rainfall analysis in Aceh Besar District with Indonesia’s Sea-Surface Temperatures as the primary component

Abstract. There are various fields that crucially require information about rainfall, including agriculture. A major drop or rise in rainfall may significantly impact the agriculture in Indonesia. For this reason, research regarding on variables that effected rainfall are still being improved by applying variety of models in order to provide accurate and closely related to the original data on rainfall forecast. Precise and accurate rainfall forecast is essential to help extension workers and farmers to determine when to start planting their crops and to decide what kind of crops are suitable for a particular region. Data applied in this research are data on monthly Sea-Surface Temperature (SST) data which are limited by 10°N – 15°S and 90°E – 145°E with a 1° x 1° grid, as well as data on monthly rainfall in Aceh Besar district which were obtained by averaging the data from 10 rain post points in collaboration with the BMKG of Aceh Besar District between 2010 – 2019. Correlation analysis between Sea-Surface Temperature (SST) and rainfall resulted in correlation value that fulfill the requirement of “sufficient” to “high” in a number of regions for each month. The highest correlation value was recorded by 0.87 for the positive correlation in October, and it was recorded by -0.87 for the highest negative value of correlation in December. Under those circumstances, by utilizing the Principal Component Regression (PCR) method, a forecasting model is created for each of the region with the highest correlation which allows for the identification of the area that most impacted rainfall in district of Aceh Besar. Model validation obtained error value of 37.1 or roughly around 19.5%. The highest value difference was occurred in October 2014, measuring by the value difference of 96 mm. The results of monthly rainfall forecast in 2021 provide a pattern of rainfall that is similar with the observation data obtained in August to December. Research results indicate that sea-surface Temperature (SST) in regions of Indonesia can be utilized as the indicator in forecasting rainfall at a district level.

Improving Monthly Rainfall Forecast in a Watershed by Combining Neural Networks and Autoregressive Models

Improving Monthly Rainfall Forecast in a Watershed by Combining Neural Networks and Autoregressive Models

Time trends, irregularity and multifractal structure on the monthly rainfall regime at Barcelona, NE Spain, years 1786–2019

AbstractA long and complete series of monthly rainfall amounts corresponding to Barcelona city (Catalonia, NE Spain), exceeding two centuries (years 1786–2019), is analysed in detail. The obtained results of periodicity (annual scale), time trends (monthly, seasonal and annual scales), statistical distribution (seasonal and annual scale) and fractal/multifractal structures and self‐similarity at monthly scale depict the complex structure of this pluviometric regime, which is characterized by moderate increasing and decreasing trends on rain amounts, varying from +0.08 mm·year−1 (February) to −0.07 mm·year−1 (September) and quite evident changes on the pluviometric trends at annual and seasonal scales when the rainfall data are analysed for segments of 50 years from 1800 up to 2019. A good example could be the relevant change on the annual scale time trend, from +0.77 mm·year−1 (years 1800–1850) to −0.17 mm·year−1 (years 1950–2019). Clear evidences of decreasing pluviometry for spring, summer and autumn for the last segment (1950–2019) in comparison with the other three segments, including years 1800–1950, are also detected. Additionally, increasing rainfall patterns complexity, expected difficulties on monthly rainfall forecasting and the increasing irregularity of monthly amounts is also detected by interpreting fractal and multifractal results. Irregularity increases on the monthly rainfall series and on the rainfall regime complexity derived from multifractal parameters, could be associated with the very notable increase of CO2 emissions into the atmosphere, globally varying from 51.1 × 106 metric tonnes (year 1820) to 36.6 × 109 metric tonnes (year 2019) and the tropospheric concentration increasing from 280.8 ppm (year 1850) to 397.5 ppm (year 2014), being the probable relationship between tropospheric concentrations and changes on rainfall patterns the objective of future researches.

A Comparison of BPNN, GMDH, and ARIMA for Monthly Rainfall Forecasting Based on Wavelet Packet Decomposition

Accurate rainfall forecasting in watersheds is of indispensable importance for predicting streamflow and flash floods. This paper investigates the accuracy of several forecasting technologies based on Wavelet Packet Decomposition (WPD) in monthly rainfall forecasting. First, WPD decomposes the observed monthly rainfall data into several subcomponents. Then, three data-based models, namely Back-propagation Neural Network (BPNN) model, group method of data handing (GMDH) model, and autoregressive integrated moving average (ARIMA) model, are utilized to complete the prediction of the decomposed monthly rainfall series, respectively. Finally, the ensemble prediction result of the model is formulated by summing the outputs of all submodules. Meanwhile, these six models are employed for benchmark comparison to study the prediction performance of these conjunction methods, which are BPNN, WPD-BPNN, GMDH, WPD-GMDH, ARIMA, and WPD-ARIMA models. The paper takes monthly data from Luoning and Zuoyu stations in Luoyang city of China as the case study. The performance of these conjunction methods is tested by four quantitative indexes. Results show that WPD can efficiently improve the forecasting accuracy and the proposed WPD-BPNN model can achieve better prediction results. It is concluded that the hybrid forecast model is a very efficient tool to improve the accuracy of mid- and long-term rainfall forecasting.

Linking Singular Spectrum Analysis and Machine Learning for Monthly Rainfall Forecasting

Monthly rainfall forecasts can be translated into monthly runoff predictions that could support water resources planning and management activities. Therefore, development of monthly rainfall forecasting models in reservoir watersheds is essential for generating future rainfall amounts as an input to a water-resources-system simulation model to predict water shortage conditions. This research aims to examine the reliability of linking a data preprocessing method (singular spectrum analysis, SSA) with machine learning, least-squares support vector regression (LS-SVR), and random forest (RF), for monthly rainfall forecasting in two reservoir watersheds (Deji and Shihmen reservoir watersheds) located in Taiwan. Merging SSA with LS-SVR and RF, the hybrid models (SSA-LSSVR and SSA-RF) were developed and compared with the standard models (LS-SVR and RF). The proposed models were calibrated and validated using the watersheds’ observed areal monthly rainfalls separated into 70 percent of data for calibration and 30 percent of data for validation. Model performances were evaluated using two accuracy measures, root mean square error (RMSE) and Nash–Sutcliffe efficiency (NSE). Results show that the hybrid models could efficiently forecast monthly rainfalls. Nonetheless, the performances of the hybrid models vary in both watersheds which suggests that prior knowledge about the watershed’s hydrological behavior would be helpful to implement the appropriate model. Overall, the hybrid models significantly surpass the standard models for the two studied watersheds, which indicates that the proposed models are a prudent modeling approach that could be employed in the current research regions for monthly rainfall forecasting.

Complete ensemble empirical mode decomposition hybridized with random forest and kernel ridge regression model for monthly rainfall forecasts

Persistent risks of extreme weather events including droughts and floods due to climate change require precise and timely rainfall forecasting. Yet, the naturally occurring non-stationarity entrenched within the rainfall time series lowers the model performances and is an ongoing research endeavour for practicing hydrologists and drought-risk evaluators. In this paper, an attempt is made to resolve the non-stationarity challenges faced by rainfall forecasting models via a complete ensemble empirical mode decomposition (CEEMD) combined with Random Forest (RF) and Kernel Ridge Regression (KRR) algorithms in designing a hybrid CEEMD-RF-KRR model in forecasting rainfall at Gilgit, Muzaffarabad, and Parachinar in Pakistan at monthly time scale. The rainfall time-series data are simultaneously factorized into respective intrinsic mode functions (IMFs) and a residual element using CEEMD. Once the significant lags of each IMF and the residual are identified, both are forecasted using the RF algorithm. Finally, the KRR model is adopted where the forecasted IMFs and the residual components are combined to generate the final forecasted rainfall. The CEEMD-RF-KRR model shows the best performances at all three sites, in comparison to the comparative models, with maximum values of correlation coefficient (0.97–0.99), Willmott’s index (0.94–0.97), Nash-Sutcliffe coefficient (0.94–0.97) and Legates-McCabe’s index (0.74–0.81). Furthermore, the CEEMD-RF-KRR model generated the most accurate results for Gilgit station considering the Legate-McCabe’s index as base assessment criteria in addition to obtaining the lowest magnitudes of RMSE = 2.52 mm and MAE = 1.98 mm. The proposed hybrid CEEMD-RF-KRR model attained better rainfall forecasting accuracy which is imperative for agriculture, water resource management, and early drought/flooding warning systems.

Streamflow and rainfall forecasting by two long short-term memory-based models

Prediction of streamflow and rainfall is important for water resources planning and management. In this study, we developed two hybrid models, based on long short-term memory network (LSTM), for monthly streamflow and rainfall forecasting. One model, wavelet-LSTM (namely, WLSTM), applied a trous algorithm of wavelet transform to do series decomposition, and the other, convolutional LSTM (namely, CLSTM), coupled convolutional neural network to extract temporal features. Two streamflow datasets and two rainfall datasets are used to evaluate the proposed models. The prediction accuracy of WLSTM and CLSTM was compared with that of multi-layer perceptron (MLP) and LSTM. Results indicated that LSTM was applicable for time series prediction, but WLSTM and CLSTM were superior alternatives.

Inter-comparison of multiple Global Climate Model (GCM) data based on spatial pattern of rainfall over Indonesia

The Coupled Model Inter-comparison Project Phase 5 (CMIP5) is the output of many coupled atmosphere-ocean of global climate models (GCMs) and widely used for climate research, especially for driving regional climate model. There are more than 40 CMIP5 GCMs data available, but no single model can be considered as the best for every region. The use of CMIP5 GCMs data for rainfall projection in Indonesia is important to improve the accuracy of the monthly and seasonal rainfall forecast. Then, this study evaluates the capability of the CMIP5 GCMs data for Indonesia region by quantitatively comparing the spatial pattern of the precipitation mean and standard deviation of the CMIP5 data against GPCP, GPCC, and CRU data in the period 1980-2005. Furthermore, the composite analysis is conducted to observe the model performance in reproducing the precipitation characteristic over some areas in Indonesia. In conclusion, the models NorESM1-M, NorESM1-ME, GFDL-ESM2M, CSIRO-MK3-6-0 perform the rainfall mean better than others, while the standard deviation of the rainfall show that the models NorESM1-M, BNU-ESM, CMCC-CMS are superior in which NorESM1-M gives the best performance. The annual precipitation pattern of the model NorESM1-M over various areas in Indonesia is also highly correlated with the observations. Thus, the most suitable model for Indonesia region is NorESM1-M.

Evaluation of preprocessing techniques for improving the accuracy of stochastic rainfall forecast models

Accurate rainfall forecasting is one of the most important and challenging hydrological modeling tasks with significant benefits for many sectors of the economy. This study presents novel insight into how to improve the accuracy of a new generation of stochastic monthly rainfall forecast models by examining four different preprocessing techniques: (1) time series modeling without preprocessing which is the common method in stochastic modeling as the base case, (2) preprocess using differencing, spectral analysis seasonal and non-seasonal standardization techniques, (3) two-step preprocessing including stationarization and normalization of data using 8 different transformations, and (4) two-step preprocessing, unlike scenario 3, so that the main time series was normalized and transformed to be stationary. Using the autocorrelation function and partial autocorrelation function diagrams, the parameters of the stochastic model are determined. The results indicate that the proposed data preprocessing normalization and transformation techniques can lead to major improvements in the prediction accuracy of the new monthly rainfall forecast model.

Forecasting extreme monthly rainfall events in regions of Queensland, Australia using artificial neural networks

Extreme rainfall in Queensland during December 2010 and January 2011 resulted in catastrophic flooding, causing loss of life, extensive property damage and major disruption of economic activity. Official medium-term rainfall forecasts failed to warn of the impending heavy rainfall. Since the flooding, the Australian Bureau of Meteorology has changed its method of forecast from an empirical statistical scheme to the application of a general circulation model (GCM), the Predictive Ocean and Atmospheric Model for Australia (POAMA). Our previous studies demonstrated that more skilful monthly rainfall forecasts can be achieved using artificial neural networks (ANNs). This study extends those previous investigations focussing on the capacity of the forecast methodology to differentiate between extreme rainfall events and more average conditions, up to one year in advance. Sites within two geographical regions of Queensland are examined: (i) coastal Queensland using rainfall observations from Bingera, Plane Creek and Victoria Mill; (ii) a region of south-east Queensland, using rainfall observations from 54 weather stations, extending approximately 300 km northward along the Queensland coast, from the Gold Coast to Bundaberg, and approximately 200 km inland. For both regions, the capacity to differentiate between average conditions and impending extreme rainfall events up to one year in advance is demonstrated.

A national-scale seasonal hydrological forecast system: development and evaluation over Britain

Abstract. Skilful winter seasonal predictions for the North Atlantic circulation and northern Europe have now been demonstrated and the potential for seasonal hydrological forecasting in the UK is now being explored. One of the techniques being used combines seasonal rainfall forecasts provided by operational weather forecast systems with hydrological modelling tools to provide estimates of seasonal mean river flows up to a few months ahead. The work presented here shows how spatial information contained in a distributed hydrological model typically requiring high-resolution (daily or better) rainfall data can be used to provide an initial condition for a much simpler forecast model tailored to use low-resolution monthly rainfall forecasts. Rainfall forecasts (hindcasts) from the GloSea5 model (1996 to 2009) are used to provide the first assessment of skill in these national-scale flow forecasts. The skill in the combined modelling system is assessed for different seasons and regions of Britain, and compared to what might be achieved using other approaches such as use of an ensemble of historical rainfall in a hydrological model, or a simple flow persistence forecast. The analysis indicates that only limited forecast skill is achievable for Spring and Summer seasonal hydrological forecasts; however, Autumn and Winter flows can be reasonably well forecast using (ensemble mean) rainfall forecasts based on either GloSea5 forecasts or historical rainfall (the preferred type of forecast depends on the region). Flow forecasts using ensemble mean GloSea5 rainfall perform most consistently well across Britain, and provide the most skilful forecasts overall at the 3-month lead time. Much of the skill (64 %) in the 1-month ahead seasonal flow forecasts can be attributed to the hydrological initial condition (particularly in regions with a significant groundwater contribution to flows), whereas for the 3-month ahead lead time, GloSea5 forecasts account for ∼ 70 % of the forecast skill (mostly in areas of high rainfall to the north and west) and only 30 % of the skill arises from hydrological memory (typically groundwater-dominated areas). Given the high spatial heterogeneity in typical patterns of UK rainfall and evaporation, future development of skilful spatially distributed seasonal forecasts could lead to substantial improvements in seasonal flow forecast capability, potentially benefitting practitioners interested in predicting hydrological extremes, not only in the UK but also across Europe.

Skilful rainfall forecasts from artificial neural networks with long duration series and single-month optimization

General circulation models, which forecast by first modelling actual conditions in the atmosphere and ocean, are used extensively for monthly rainfall forecasting. We show how more skilful monthly and seasonal rainfall forecasts can be achieved through the mining of historical climate data using artificial neural networks (ANNs). This technique is demonstrated for two agricultural regions of Australia: the wheat belt of Western Australia and the sugar growing region of coastal Queensland. The most skilful monthly rainfall forecasts measured in terms of Ideal Point Error (IPE), and a score relative to climatology, are consistently achieved through the use of ANNs optimized for each month individually, and also by choosing to input longer historical series of climate indices. Using the longer series restricts the number of climate indices that can be used.

A Comparison of Three Soft Computing Techniques, Bayesian Regression, Support Vector Regression, and Wavelet Regression, for Monthly Rainfall Forecast

Abstract Rainfall, being one of the most important components of the hydrological cycle, plays an extremely important role in agriculture-based economies like India. This paper presents a comparison between three soft computing techniques, namely Bayesian regression (BR), support vector regression (SVR), and wavelet regression (WR), for monthly rainfall forecast in Assam, India. A WR model is a combination of discrete wavelet transform and linear regression. Monthly rainfall data for 102 years from 1901 to 2002 at 21 stations were used for this study. The performances of different models were evaluated based on the mean absolute error, root mean square error, correlation coefficient, and Nash-Sutcliffe efficiency coefficient. Based on model statistics, WR was found to be the most accurate followed by SVR and BR. The efficiencies for the BR, SVR, and WR models were found to be 32.8%, 52.9%, and 64.03%, respectively. From the spatial analysis of model performances, it was found that the models performed best for the upper Assam region followed by lower, southern, and middle regions, respectively.

Monthly Rainfall Forecasting Using EEMD-SVR Based on Phase-Space Reconstruction

Rainfall links atmospheric and surficial processes and is one of the most important hydrologic variables. We apply support vector regression (SVR), which has a high generalization capability, to construct a rainfall forecasting model. Before construction of the model, a self-adaptive data analysis methodology called ensemble empirical mode decomposition (EEMD) is used to preprocess a rainfall data series. In addition, the phase-space reconstruction method is implemented to design input vectors for the forecasting model. The proposed hybrid model is applied to forecast the monthly rainfall at a weather station in Changchun, China as a case study. To demonstrate the capacity of the proposed hybrid model, a typical three-layer feed-forward artificial neural network model, an auto-regressive integrated moving average model, and a support vector regression model are constructed. Predictive performance of the models is evaluated based on normalized mean squared error (NMSE), mean absolute percent error (MAPE), Nash–Sutcliffe efficiency (NSE), and the coefficient of correlation (CC). Results indicate that the proposed hybrid model has the lowest NMSE and MAPE values of 0.10 and 14.90, respectively, and the highest NSE and CC values of 0.91 and 0.83, respectively, during the validation period. We conclude that the proposed hybrid model is feasible for monthly rainfall forecast and is better than the models currently in common use.

Stochastic Monthly Rainfall Time Series Analysis, Modeling and Forecasting in Kavala City, Greece, North-Eastern Mediterranean Basin

Rainfall is one of the most important sources of water on earth supporting the existence of the majority of living organisms. Time series analysis, modeling and forecasting constitutes a tool of paramount importance with reference to a wide range of scientific purposes in meteorology (e.g. precipitation, humidity, temperature, solar radiation, floods and draughts). The present research applies the Box-Jenkins approach, employing SARIMA (Seasonal Autorregressive Integrated Moving Average) model to perform short term forecasts of monthly rainfall in Kavala city, Kavala Prefecture, Region of Eastern Macedonia-Thrace, North-Eastern Greece, North-Eastern Mediterranean Basin, modeling past rainfall time series components structure and predicting future quantities in accordance to the past. The model which is mostly fit to both describe the past rainfall data and thus generate the most reliable future forecasts is selected rated by means of both the AIC- and BIC- (SBC-) model evaluation criteria. The conclusions of this research will provide local authorities (e.g. General Secretariat for Civil Protection, European Center for Forest Fires, Deputy Governor of Agricultural Economy, daily fire risk maps designers, hydraulic, irrigation and environmental engineers, city inhabitants, farmers etc.) to develop strategic plans, policies and appropriate use of available water resources in Kavala city district.

Assessing the quality of eight different maximum temperature time series as inputs when using artificial neural networks to forecast monthly rainfall at Cape Otway, Australia

Temperature time series are important inputs for monthly rainfall forecasting when using statistical models including artificial neural networks. The longest continuous time series, unaffected by urban heat islands (UHIs), for anywhere in Australia, have been recorded at lighthouses. These are generally truncated and homogenized in order to correct for non-climatic factors including changes in equipment before calculating climatic trends and/or incorporation into statistical models. There has been no objective measure, however, of the skill of the different homogenization techniques. In this study, the skill of the monthly rainfall forecast for Cape Otway for the period from September 2005 to December 2013 is used as an indirect measure of the quality of eight different maximum temperature series developed from three different homogenization techniques applied to data from Cape Otway lighthouse, and also the nearby Wilsons Promontory lighthouses. The homogenized, and also raw temperature series, were used as input into artificial neural network models as part of multi-dimensional data arrays that included lagged climate indices. The most skilful set of monthly rainfall forecasts was derived from a raw maximum temperature series, paired with a homogenized minimum series, both from Wilsons Promontory lighthouse. The mean warming trend for this paired series for the period 1887 to 2013 is 0.8°C per century, which is consistent with the global land surface temperature increase since 1880. All series show significant cooling of maximum temperatures from 1921 to 1950, which is at variance with Australian and global homogenized temperature series. The significant warmth in the early un-homogenized maximum temperature time series for Cape Otway is shown to be spurious.

A hybrid wavelet neural network model with mutual information and particle swarm optimization for forecasting monthly rainfall

In this paper, a hybrid wavelet neural network (HWNN) model is developed for effectively forecasting monthly rainfall from antecedent monthly rainfall and climate indices by incorporating the multiresolution analysis (MRA), mutual information (MI) and particle swarm optimization (PSO) into artificial neural network (ANN) models. The standardized monthly rainfall anomaly and large-scale climate indices are first decomposed by using the maximal overlap discrete wavelet transform (MODWT) into a certain number of subseries components with different time scales. Then at each time scale, a small and appropriate subset of ANN inputs is identified by the modified partial MI algorithm from a set of candidate subseries components with different lags for forecasting the rainfall anomaly subseries at the corresponding scale. The optimal number of neurons in the hidden layers of ANNs is determined by PSO algorithm, and then each of rainfall anomaly subseries is forecasted from the selected predictor subseries. Finally, the monthly rainfall forecast is achieved by summing all the predicted anomaly subseries and applying the inverse transform of standardized monthly rainfall. The proposed HWNN method is examined with 255 rain gauge stations over Australia, and compared to the reference methods based on the undecomposed time series. The forecasting performance is compared with observed rainfall values, and evaluated by common statistics of relative absolute error and Nash–Sutcliffe efficiency. The results show that the HWNN model improves the monthly rainfall forecasting accuracy over Australia in comparison to the reference models, and the improvement is more significant for the inland stations in southeast Australia and stations in west Australia.